Skip to content

Merge Gateway

Pricing page

208 listings across 195 models

Page 6 of 8. The lists below split this page's listings into those sold by Merge Gateway, run by Merge Gateway, or sent to Merge Gateway by a marketplace.

Sold by Merge Gateway

25 listings on this page sold by Merge Gateway.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
$0.56cache read $0.13$1.68131KNot measured
Devstral 2 123b Instruct 2512mistral/devstral-2512
$0.40cache read $0.04$2.00256KNot measuredNot measured
$0.287cache read $0.0574$1.147131KNot measured
Qwen3 Coderqwen/qwen3-coder-480b-a35b-instruct
$0.22$1.80131KNot measured
MiniMax M2
$0.30cache read $0.03$1.20cache write $0.375205KNot measuredNot measured
Seed 2.0 Minibytedance/dola-seed-2.0-mini
Not enough data yet$0.12$0.50256KNot measuredNot measured
GPT OSS 120B
$0.05$0.25128K
$0.15cache read $0.075$0.80262KNot measured
Mistral Large 3mistral/mistral-large-2512
$0.50cache read $0.05$1.50256KNot measured
$0.10cache read $0.05$1.10131KNot measuredNot measured
GLM 4.5 Air
$0.20cache read $0.03$1.10128KNot measuredNot measured
Not enough data yet$2.50$10.00256KNot measuredNot measured
Devstral Mediummistral/devstral-medium-latest · latest
Not enough data yet$0.40$2.00262KNot measuredNot measured
Codestral 25.01mistral/codestral-latest · latest
Not enough data yet$0.30$0.90256KNot measured
Qwen Plus
Not enough data yet$0.115cache read $0.023$0.287cache write $0.14381MNot measuredNot measured
GPT-4 Turbo
$10.00$30.00128KNot measured
GLM 4.7 Flash
$0.07$0.40200KNot measuredNot measured
GLM 4.5V
Not enough data yet$0.60cache read $0.11$1.80128KNot measuredNot measured
Not enough data yet$0.50$3.0033KNot enough data yetNot measuredNot measured
Qwen3 32B
$0.15$0.60131KNot measured
GPT-4.1 mini
$0.40cache read $0.10$1.601MNot measured
GPT-5 nano
$0.05cache read $0.005$0.40400K
Mistral Mediummistral/mistral-medium-latest · latest
$0.40$2.00262KNot measured
DeepSeek V3
$0.27$1.10164K
——1MNot measuredNot measured

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works